Retrieval-Augmented Generation104 · Module III · Lesson 08 of 13
Article · 12 min

Ranking and reranking

The improvement most systems skip.

Summary

Retrieval returns 50-200 candidates; the generator can only use 5-20. A reranker sits between: a smaller model that scores each candidate against the query with more expressiveness than a raw dot product. Adding a reranker is the highest-return improvement most RAG systems have not made.

Objectives
  • 01Distinguish retrieval, ranking, and reranking.
  • 02Name the two dominant reranker types.
  • 03State the latency cost of adding a reranker.
The Lesson

The stage

Retrieval returns candidates by rough similarity. The reranker scores each candidate against the query with a cross-encoder that reads query and document jointly. Higher quality than a dot product; slower.

Choices

Cohere Rerank, Voyage rerank, or open-source (BGE, Jina rerankers). Latency: 50-200ms for 50 candidates. Nearly always worth it. LLM-as-reranker works but costs more; use for the top 10-20 after a cheaper reranker.

Key Ideas
  • Reranking is the highest-return upgrade for most RAG systems.
  • Cross-encoders beat dot products at a cost most systems can pay.